Liste complète des publications

Christophe Cerisara

17 janvier 2022

Thèses

[1]   C. cerisara : Quelques contributions en reconnaissance automatique de la parole robuste, mars 2010. Habilitation à diriger des recherches de l’Université Henri Poincaré, Nancy 1.

[2]   C. cerisara : Contribution de l’approche Multi-Bandes à la reconnaissance automatique de la parole. Thèse de doctorat, Institut National Polytechnique de Lorraine, LORIA, Nancy, France, sept. 1999.

Livres et chapitres de livres

[3]   J.-P. haton, C. cerisara, D. fohr, Y. laprie et K. smaïli : Reconnaissance automatique de la parole : du signal à son interprétation. Dunod, mai 2006.

[4]   C. cerisara et Y. haradji : Informatique diffuse, chap. Nouvelles formes d’interaction homme-machine pour l’informatique diffuse. OFTA, mai 2007.

[5]   G. georgantas, V. issarny et C. cerisara : Ambient Intelligence, Wireless Networking, and Ubiquitous Computing, chap. Dynamic Synthesis of Natural Human-Machine Interfaces in Ambient Intelligence Environments. Artech House, juil. 2006.

[6]   C. cerisara : Computational Models of Speech Pattern Processing, chap. Dealing With Loss of Synchronism in Multi-Band Continuous Speech Recognition Systems. NATO ASI Series F, 1999.

Revues internationales avec comité de lecture

[7]   C. cerisara, P. král et L. lenc : On the effects of using word2vec representations in neural networks for dialogue act recognition. Computer Speech & Language, 47:175 – 193, 2018.

[8]   P. kral et C. cerisara : Automatic dialogue act recognition with syntactic features. Language Resources and Evaluation, 48(3):419–441, 2014.

[9]   P. kral et C. cerisara : Dialogue act recognition approaches. Computing and Informatics, 29(2):227–250, 2010.

[10]   C. cerisara : Automatic discovery of topics and acoustic morphemes from speech. Computer Speech and Language, 23(2):220–239, avr. 2009.

[11]   S. demange, C. cerisara et J.-P. haton : Missing data mask estimation with frequency and temporal dependencies. Computer Speech and Language, 23(1):25–41, 2009.

[12]   C. cerisara, S. demange et J.-P. haton : On noise masking for automatic missing data speech recognition : a survey and discussion. Computer Speech and Language, 21(3):443–457, juil. 2007.

[13]   P. král, C. cerisara et J. klečková : Lexical structure for dialogue act recognition. Journal of Multimedia, 2(3):1–8, juin 2007.

[14]   C. cerisara, L. rigazio et J.-C. junqua : α-jacobian environmental adaptation. Speech Communication, 42(1):25–41, jan. 2004. Special Issue on Adaptation Methods for Automatic Speech Recognition.

[15]   C. cerisara et D. fohr : Multi-Band automatic speech recognition. Computer Speech and Language, 15(2):151–174, avr. 2001.

Conférences internationales avec comité de lecture

[16]   C. cerisara et A. cuzzocrea : Unsupervised Risk for Privacy. In IEEE BigData, Special Session on Privacy and Security of Big Data, Orlando, United States, déc. 2021.

[17]   F. gontier, R. serizel et C. cerisara : AUTOMATED AUDIO CAPTIONING BY FINE-TUNING BART WITH AUDIOSET TAGS. In The 6th Workshop on Detection and Classification of Acoustic Scenes and Events, DCASE 2021, Virtual, Spain, nov. 2021.

[18]   P. caillon et C. cerisara : Growing Neural Networks Achieve Flatter Minima. In ICANN 2021 - 30th International Conference on Artificial Neural Networks, vol. 12892 de Lecture Notes in Computer Science, p. 222–234, Bratislava, Slovakia, sept. 2021. Springer International Publishing.

[19]   A. chaoub, A. voisin, C. cerisara et B. iung : Learning representations with end-to-end models for improved remaining useful life prognostic. In PHM Society European Conference, vol. 6, 2021.

[20]   C. cerisara, P. caillon et G. le berre : Unsupervised post-tuning of deep neural networks. In Proc. IJCNN, Proceedings of the 2021 International Joint Conference on Neural Networks, Virtual Event, United States, juil. 2021.

[21]   G. le berre et C. cerisara : Seq-to-NSeq model for multi-summary generation. In ESANN 2020, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, oct. 2020.

[22]   H. T. le, C. cerisara et C. gardent : Quality of syntactic implication of RL-based sentence summarization. In AAAI Workshop on Engineering Dependable and Secure Machine Learning Systems 2020, EDSMLS, New York, United States, fév. 2020.

[23]   H. T. le, C. cerisara et C. gardent : RL extraction of syntax-based chunks for sentence compression. In ICANN 2019, Munich, Germany, sept. 2019.

[24]   H. nourtel, C. cerisara et S. cruz-lara : Deep unsupervised system log monitoring. In PROFES 2019 - 20th International Conference on Product-Focused Software Process Improvement, Barcelona, Spain, nov. 2019.

[25]   J. martínek, P. kral, L. lenc et C. cerisara : Multi-Lingual Dialogue Act Recognition with Deep Learning Methods. In Proc. Interspeech, Graz, Austria, sept. 2019.

[26]   C. cerisara, S. jafaritazehjani, A. oluokun et H. T. le : Multi-task dialog act and sentiment recognition on Mastodon. In COLING, Santa Fe, United States, août 2018.

[27]   H. T. le, C. cerisara et A. denis : Do Convolutional Networks need to be Deep for Text Classification ? In AAAI Workshop on Affective Content Analysis , New Orleans, United States, fév. 2018.

[28]    G. serrière, C. cerisara, D. fohr et O. mella : Weakly-supervised text-to-speech alignment confidence measure. In International Conference on Computational Linguistics (COLING), Osaka, Japan, déc. 2016.

[29]   B. gyawali, C. gardent et C. cerisara : Automatic Verbalisation of Biological Events. In International Workshop on Definitions in Ontologies (IWOOD 2015), Lisbon, Portugal, juil. 2015.

[30]   B. gyawali, C. gardent et C. cerisara : A Domain Agnostic Approach to Verbalizing n-ary Events without Parallel Corpora. In Proceedings of the 15th European Workshop on Natural Language Generation (ENLG), p. 18–27, Brighton, United Kingdom, sept. 2015.

[31]   L. M. rojas barahona et C. cerisara : Weakly supervised discriminative training of linear models for Natural Language Processing. In 3rd International Conference on Statistical Language and Speech Processing (SLSP), Budapest, Hungary, nov. 2015.

[32]   L. M. rojas barahona et C. cerisara : Enhanced discriminative models with tree kernels and unsupervised training for entity detection. In 6th. International Conference on Information Systems & Economic Intelligence (SIIE), Hammamet, Tunisia, fév. 2015.

[33]   P. kral, L. lenc et C. cerisara : Semantic Features for Dialogue Act Recognition. In 3rd International Conference on Statistical Language and Speech Processing (SLSP), Budapest, Hungary, nov. 2015.

[34]   C. cerisara : Semi-supervised experiments at LORIA for the SPMRL 2014 Shared Task. In Proc. of the Shared Task on Statistical Parsing of Morphologically Rich Languages, Dublin, Ireland, août 2014.

[35]   L. M. rojas barahona et C. cerisara : Bayesian inverse reinforcement learning for modeling conversational agents in a virtual environment. In Proc. conf. on Intelligent Text Processing and Computational Linguistics, Kathmandu, Nepal, avr. 2014.

[36]   A. lorenzo et C. cerisara : Semi-supervised srl system with bayesian inference. In Proc. conf. on Intelligent Text Processing and Computational Linguistics, Kathmandu, Nepal, avr. 2014.

[37]   F. bimbot, C. cerisara, C. fougeron, G. gravier, L. lamel, F. pellegrino et P. perrier : Proceedings of the 14th annual conference of the international speech communication association (interspeech). In Proc. Interspeech, Lyon, France, août 2013.

[38]   C. cerisara, A. lorenzo et P. kral : Weakly supervised parsing with rules. In Proc. Interspeech, p. 2192–2196, Lyon, France, août 2013.

[39]   A. lorenzo, L. M. rojas barahona et C. cerisara : Unsupervised structured semantic inference for spoken dialog reservation tasks. In Proc. SIGDIAL Meeting on Discourse and Dialogue, p. 12–20, Metz, France, août 2013.

[40]   C. cerisara et A. lorenzo : Mixed probabilistic and deterministic dependency parsing. In Proc. Interspeech, p. 4, Portland, Oregon, août 2012.

[41]   A. lorenzo et C. cerisara : Unsupervised frame based Semantic Role Induction : application to French and English. In Proceedings of the ACL 2012 Joint Workshop on Statistical Parsing and Semantic Processing of Morphologically Rich Languages, p. 30–35, Jeju, Republic of Korea, juil. 2012.

[42]   C. cerisara et C. gardent : The JSafran platform for semi-automatic speech processing. In Proc. Interspeech, p. 4, Firenze, Italy, août 2011.

[43]   C. cerisara, P. král et C. gardent : Commas recovery with syntactic features in French and in Czech. In Proc. Interspeech, p. 4, Firenze, Italy, août 2011.

[44]   C. gillot et C. cerisara : Similarity language model. In Proc. Interspeech, p. 4, Firenze, Italy, août 2011.

[45]    C. gardent et C. cerisara : Semi-automatic semantic pre-annotation for French. In Proc. Intl Workshop on Treebanks and Linguistic Theories (TLT), Tartu, Estonia, déc. 2010.

[46]   C. cerisara, C. gardent et C. anderson : Building and exploiting a dependency treebank for French radio broadcasts. In Proc. Intl Workshop on Treebanks and Linguistic Theories (TLT), Tartu, Estonia, déc. 2010.

[47]   F. tantini, C. cerisara et C. gardent : Memory-based active learning for French broadcast news. In Proc. Interspeech, p. 1377–1380, Tokyo, Japan, sept. 2010.

[48]   C. gillot, C. cerisara, D. langlois et J.-P. haton : Similar n-gram language model. In Proc. Interspeech, p. 1824–1827, Tokyo, Japan, sept. 2010.

[49]   C. cerisara, O. mella et D. fohr : Jtrans, an open-source software for semi-automatic text-to-speech alignment. In Proc. Interspeech, Brighton, UK, sept. 2009.

[50]   P. král, T. pavelka et C. cerisara : Evaluation of dialogue act recognition approaches. In Proc. IEEE Workshop on Machine Learning for Signal Processing, Cancun, Mexico, oct. 2008.

[51]   C. cerisara : Exploiting confidence measures for missing data speech recognition. In Proc. Acoustics, Paris, juil. 2008.

[52]   P. král, C. cerisara et J. klečková : Importance of prosody for dialogue acts recognition. In Proc. SPECOM, Moscow, Russia, oct. 2007.

[53]   S. demange, C. cerisara et J.-P. haton : Accurate marginalization range for missing data recognition. In Proc. Interspeech, août 2007.

[54]   P. král, C. cerisara et J. klečková : Confidence measures for semi-automatic labelling of dialog acts. In Proc. ICASSP, p. 153–156, Honolulu, Hawaii, USA, avr. 2007.

[55]   S. demange, C. cerisara et J.-P. haton : Missing data mask models with global frequency and temporal constraints. In Proc. Interspeech, Pittsburgh, Pennsylvania USA, sept. 2006.

[56]   P. král, J. klečková et C. cerisara : Automatic dialog acts recognition based on words clusters. In 9th Western Pacific Acoustics Conference - WESPAC IX 2006, p. 6 p. The Acoustical Society of Korea, juin 2006.

[57]   C. cerisara et K. daoudi : Evaluation of the SPACE denoising algorithm on aurora2. In Proc. ICASSP, Toulouse, mai 2006.

[58]   S. demange, C. cerisara et J.-P. haton : Mask estimation for missing data recognition using background noise sniffing. In Proc. ICASSP, Toulouse, mai 2006.

[59]   P. král, C. cerisara et J. klečková : Automatic dialog acts recognition based on sentence structure. In ieee, éd. : Proc. ICASSP, p. 61–64. IEEE, mai 2006.

[60]   P. král, C. cerisara, J. klečková et T. pavelka : Sentence structure for dialog act recognition in czech. In 2nd IEEE International Conference on Information et Communication Technologies : from Theory to Applications - ICTTA’06. Syrian Computer Society, SCS, avr. 2006.

[61]   K. daoudi et C. cerisara : An improved version of the SPACE algorithm for noise robust speech recognition. In Proc. IEEE-EURASIP ISCCSP, Marrakech, Morroco, mars 2006.

[62]   P. král, C. cerisara et J. klečková : Combination of classifiers for automatic recognition of dialog acts. In Proc. Interspeech, p. 825–828, 2005.

[63]   P. král, J. klečková et C. cerisara : Sentence modality recognition in French based on prosody. In VI. International Conference on Enformatika, Systems Sciences and Engineering - ESSE 2005, p. 185–188, 2005.

[64]   K. daoudi et C. cerisara : The MAP-SPACE denoising algorithm for noise robust speech recognition. In Proc. IEEE ASRU Workshop, Cancuun, Mexique, 2005.

[65]   P. král, J. klečková et C. cerisara : Analysis of importance of the prosodic features for automatic sentence modality recognition in French in real conditions. In Proc. ICECS, vol. 3, p. 1820–1824, Crete, Greece, nov. 2004.

[66]   I. illina, D. fohr, O. mella et C. cerisara : The automatic news transcription system : Ants, some real time experiments. In Proc. ICSLP, Jeju island, Korea, oct. 2004.

[67]   D. fohr, O. mella, I. illina et C. cerisara : Experiments on the accuracy of phone models and liaison processing in a French broadcast news transcription system. In Proc. ICSLP, Jeju island, Korea, oct. 2004.

[68]   C. cerisara, D. fohr, O. mella et I. illina : Exploiting models intrinsic robustness for noisy speech recognition. In Proc. ICSLP, Jeju island, Korea, oct. 2004.

[69]   C. cerisara et I. illina : Robust speech recognition to non-stationary noise based on model-driven approaches. In EUROSPEECH’2003, Geneva, Switzerland, sept. 2003.

[70]   C. cerisara : Towards missing data recognition with cepstral features. In EUROSPEECH’2003, Geneva, Switzerland, sept. 2003.

[71]   C. cerisara et D. fohr : Fast channel and noise compensation in the spectral domain. In EUSIPCO 2002, Toulouse, France, sept. 2002.

[72]   C. cerisara, J.-C. junqua et L. rigazio : Dynamic estimation of a noise over estimation factor for Jacobian-based adaptation. In ICASSP 2002, Orlando, Floride, May 2002.

[73]    C. cerisara, L. rigazio, R. boman et J.-C. junqua : Environmental adaptation based on first order approximation. In ICASSP 2001, Salt lake City, USA, mai 2001.

[74]   C. cerisara, D. fohr, I. illina, F. lauri et O. mella : Comparison of different methods for noise adaptation in a HMM-based speech recognition system . In International Congress on Acoustics, Italy, Rome, sept. 2001.

[75]   C. cerisara et K. daoudi : Modeling dependency between regression classes in MLLR using multiscale autoregressive models. In Workshop on adaptation methods for speech recognition, Sophia-Antipolis, France, août 2001.

[76]   J.-C. junqua, C. cerisara, L. rigazio et D. kryze : Environment-adaptive algorithms for robust speech recognition. In Workshop on Hands-Free Speech Communication, Kyoto, Japan, avr. 2001.

[77]   C. cerisara, L. rigazio, R. boman et J.-C. junqua : Transformation of Jacobian matrices for noisy speech recognition. In Proc. ICSLP, vol. 1, p. 369–372, Beijing, China, oct. 2000.

[78]   C. cerisara, D. fohr et J.-P. haton : Asynchrony in Multi-Band Speech Recognition. In IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP’2000, Istanbul, juin 2000.

[79]   R. boman, C. cerisara, L. rigazio et J.-C. junqua : Jacobian adaptation and likelihood computation for speech recognition on inexpensive integer processors. In ICSPAT, Dallas, Texas, oct. 2000.

[80]   J.-P. haton, C. cerisara et D. fohr : Improvement of Multi-Band Speech Recognition. In SPECOM’99, 1999.

[81]   C. cerisara, D. fohr et J.-P. haton : Robust behavior of multi-band paradigm. In Robust Methods for Speech Recognition in Adverse Conditions, Tampere. Nokia, COST249 and IEEE, mai 1999.

[82]   C. cerisara, J.-P. haton et D. fohr : Towards a Global Optimization Scheme for Multi-Band Speech Recognition. In EUROSPEECH’99, Prague, sept. 1999.

[83]   C. cerisara, J.-P. haton, J.-F. mari et D. fohr : A Recombination Model for Multi-Band Speech Recognition. In ICASSP’98, Seattle, USA, mai 1998.

[84]   C. cerisara, J.-P. haton, J.-F. mari et D. fohr : Multi-Band Continuous Speech Recognition. In EUROSPEECH, 1997.

Conférences francophones avec comité de lecture

[85]   C. anderson, C. cerisara et C. gardent : Vers la détection des dislocations à gauche dans les transcriptions automatiques du français parlé. In Proc. TALN, p. 6, Montpellier, juin 2010. ATALA.

[86]   C. cerisara et C. gardent : Analyse syntaxique du français parlé. In Workshop ATALA, Paris, oct. 2009.

[87]    A. brun, C. cerisara, D. fohr, I. illina, D. langlois, O. mella et K. smaïli : Ants  : le système de transcription automatique du loria. In Journées d’Études sur la Parole, Fès, Maroc, avr. 2004.

[88]   D. fohr, O. mella, I. illina, F. lauri, C. cerisara et C. antoine : Reconnaissance de la parole pour des locuteurs non natifs en présence de bruit. In Journées d’Études sur la Parole, Nancy, France, 2002.

[89]   C. cerisara, M. afify et J.-P. haton : étude de la recombinaison de plusieurs classifieurs appliquée à deux tâches de reconnaissance de la parole. In Journées d’Études sur la Parole, Martigny, Suisse, juin 1998.

[90]   C. cerisara, Y. gong et J.-P. haton : Reconnaissance de la parole continue par le modèle STM polynomial. In Journées d’Études sur la Parole, Avignon, France, 1996.

Divers

[91]   H. T. le, C. cerisara et A. denis : Report Transfer Learning of Deep Convolutional Network on Twitter. Research report, Loria & Inria Grand Est, juil. 2017.

[92]   D. sacchetti, R. chibout, V. issarny, C. cerisara et F. landragin : Seamless access to mobile services for the mobile user. Demonstration, ASE’04 Conference, sept. 2004.

[93]   Y. laprie et C. cerisara : Vers le succès en reconnaissance vocale. Inédit, la lettre d’information de l’INRIA, mars 2004. Numéro spécial "Le hasard et l’observation".

[94]   D. sacchetti, A. talamona, V. issarny, S. ben attalah, C. cerisara, R. chibout et W. van raemdonck : Ozone away environment. Film de démonstration, diffusion INRIA, 2004.